Training in progress, epoch 2, checkpoint

checkpoint-82/config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "allenai/longformer-base-4096",
+  "architectures": [
+    "LongformerForTokenClassification"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700,
+    700
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B",
+    "2": "I"
+  },
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B": 1,
+    "I": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

checkpoint-82/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae7f6009858cd80989f625d187716e434919a282b4e2495fdddb7d467153a4c
+size 592318676

checkpoint-82/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67afd504adee65842b24b6efeda532ff782e679eb0932c95531b3561a09b92e1
+size 1014645498

checkpoint-82/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89877ef9e20371f8fe0b9908da02b2f9df9183d72fe426c751529fa8e0e2e0e2
+size 14244

checkpoint-82/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35becfc5c99f2600532b4996a243492c9f70147154c4888c3394125f10b7908d
+size 1064

checkpoint-82/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-82/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LongformerTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-82/trainer_state.json

@@ -0,0 +1,111 @@
+{
+  "best_metric": 0.10394605249166489,
+  "best_model_checkpoint": "longformer-spans/checkpoint-82",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 82,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_B": {
+        "f1-score": 0.773921200750469,
+        "precision": 0.8258258258258259,
+        "recall": 0.7281553398058253,
+        "support": 1133.0
+      },
+      "eval_I": {
+        "f1-score": 0.9504992905522983,
+        "precision": 0.9305934158104424,
+        "recall": 0.9712753734201456,
+        "support": 18277.0
+      },
+      "eval_O": {
+        "f1-score": 0.9060251089982665,
+        "precision": 0.9388199433921185,
+        "recall": 0.8754441173484926,
+        "support": 9851.0
+      },
+      "eval_accuracy": 0.9295991251153413,
+      "eval_loss": 0.20753507316112518,
+      "eval_macro avg": {
+        "f1-score": 0.8768152001003445,
+        "precision": 0.8984130616761289,
+        "recall": 0.8582916101914878,
+        "support": 29261.0
+      },
+      "eval_runtime": 1.3745,
+      "eval_samples_per_second": 58.203,
+      "eval_steps_per_second": 7.275,
+      "eval_weighted avg": {
+        "f1-score": 0.9286894365406706,
+        "precision": 0.9293063047668868,
+        "recall": 0.9295991251153413,
+        "support": 29261.0
+      },
+      "step": 41
+    },
+    {
+      "epoch": 2.0,
+      "eval_B": {
+        "f1-score": 0.8532477947072975,
+        "precision": 0.7817781043350478,
+        "recall": 0.93909973521624,
+        "support": 1133.0
+      },
+      "eval_I": {
+        "f1-score": 0.9757511140271741,
+        "precision": 0.9750846901977925,
+        "recall": 0.9764184494173004,
+        "support": 18277.0
+      },
+      "eval_O": {
+        "f1-score": 0.9535708776800864,
+        "precision": 0.9661387789122734,
+        "recall": 0.9413257537305857,
+        "support": 9851.0
+      },
+      "eval_accuracy": 0.9631591538224941,
+      "eval_loss": 0.10394605249166489,
+      "eval_macro avg": {
+        "f1-score": 0.927523262138186,
+        "precision": 0.9076671911483712,
+        "recall": 0.9522813127880422,
+        "support": 29261.0
+      },
+      "eval_runtime": 1.3627,
+      "eval_samples_per_second": 58.708,
+      "eval_steps_per_second": 7.338,
+      "eval_weighted avg": {
+        "f1-score": 0.9635405344487392,
+        "precision": 0.9645880382085871,
+        "recall": 0.9631591538224941,
+        "support": 29261.0
+      },
+      "step": 82
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 205,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 287573305471200.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-82/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e6096217861fceecf3217bccfb927eedaa1468f412305cbdb6fb177b899ee2
+size 5240